Skip to content

OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.

Python

made updates happen depending on what part of the onboarding we are

Lucas Oliveira4449b6352c35
diff --git a/src/api/settings.py b/src/api/settings.py
index 5570c7b48..8d71ad768 100644
--- a/src/api/settings.py
+++ b/src/api/settings.py
@@ -1110,12 +1110,12 @@ async def onboarding(
current_config.providers.any_configured()):
await _update_langflow_global_variables(current_config, flows_service=flows_service)
+ if body.llm_provider or body.llm_model and not (body.embedding_provider or body.embedding_model):
+ await _update_langflow_model_values(current_config, flows_service, llm_model=body.llm_model, llm_provider=body.llm_provider)
+
if body.embedding_provider or body.embedding_model:
await _update_mcp_servers_with_provider_credentials(current_config, session_manager=session_manager, flows_service=flows_service)
-
- # Update model values if provider or model fields were provided
- if body.llm_provider or body.llm_model or body.embedding_provider or body.embedding_model:
- await _update_langflow_model_values(current_config, flows_service, body.llm_model, body.llm_provider, body.embedding_model, body.embedding_provider)
+ await _update_langflow_model_values(current_config, flows_service, embedding_model=body.embedding_model, embedding_provider=body.embedding_provider)
except Exception as e:
logger.error(
@@ -1479,57 +1479,58 @@ async def _update_mcp_servers_with_provider_credentials(config, session_manager
# Don't fail the entire settings update if MCP update fails
-async def _update_langflow_model_values(config, flows_service, llm_model, llm_provider, embedding_model, embedding_provider):
+async def _update_langflow_model_values(config, flows_service, llm_model=None, llm_provider=None, embedding_model=None, embedding_provider=None):
"""Update model values across Langflow flows for all configured providers"""
try:
- # 1. Update ONLY the current LLM provider
- llm_provider = llm_provider.lower() if llm_provider else config.agent.llm_provider.lower()
- llm_model = llm_model if llm_model else config.agent.llm_model
- flows_service.change_langflow_model_value(
- llm_provider,
- llm_model=llm_model,
- force_llm_update=True
- )
-
-
- if embedding_provider and embedding_model:
- result = await flows_service.change_langflow_model_value(
- embedding_provider,
- embedding_model=embedding_model,
- force_embedding_update=True
+ if not embedding_model and not embedding_provider:
+ # 1. Update ONLY the current LLM provider
+ current_llm_provider = llm_provider.lower() if llm_provider else config.agent.llm_provider.lower()
+ current_llm_model = llm_model if llm_model else config.agent.llm_model
+ await flows_service.change_langflow_model_value(
+ current_llm_provider,
+ llm_model=current_llm_model,
+ force_llm_update=True
)
- logger.info(
- f"Successfully updated Langflow flows for embedding provider {embedding_provider}",
- result=result
- )
- else:
- # 2. Update ALL configured embedding providers
- embedding_providers = []
- if config.providers.openai.configured:
- embedding_providers.append("openai")
- if config.providers.watsonx.configured:
- embedding_providers.append("watsonx")
- if config.providers.ollama.configured:
- embedding_providers.append("ollama")
-
- current_embedding_provider = config.knowledge.embedding_provider.lower()
- for provider in embedding_providers:
- # Use configured model for current provider, or None (first available) for others
- embedding_model = (
- config.knowledge.embedding_model
- if provider == current_embedding_provider
- else None
+ if not llm_model and not llm_provider:
+ if embedding_provider and embedding_model:
+ result = await flows_service.change_langflow_model_value(
+ embedding_provider,
+ embedding_model=embedding_model,
+ force_embedding_update=True
)
- await flows_service.change_langflow_model_value(
- provider,
- embedding_model=embedding_model,
- force_embedding_update=True
- )
+
logger.info(
- f"Successfully updated Langflow flows for embedding provider {provider}"
+ f"Successfully updated Langflow flows for embedding provider {embedding_provider}",
+ result=result
)
+ else:
+ # 2. Update ALL configured embedding providers
+ embedding_providers = []
+ if config.providers.openai.configured:
+ embedding_providers.append("openai")
+ if config.providers.watsonx.configured:
+ embedding_providers.append("watsonx")
+ if config.providers.ollama.configured:
+ embedding_providers.append("ollama")
+
+ current_embedding_provider = config.knowledge.embedding_provider.lower()
+ for provider in embedding_providers:
+ # Use configured model for current provider, or None (first available) for others
+ embedding_model = (
+ config.knowledge.embedding_model
+ if provider == current_embedding_provider
+ else None
+ )
+ await flows_service.change_langflow_model_value(
+ provider,
+ embedding_model=embedding_model,
+ force_embedding_update=True
+ )
+ logger.info(
+ f"Successfully updated Langflow flows for embedding provider {provider}"
+ )
except Exception as e:
logger.error(f"Failed to update Langflow model values: {str(e)}")
raise